| 1 | # SPDX-License-Identifier: Apache-2.0 |
| 2 | # SPDX-FileCopyrightText: Copyright contributors to the vLLM project |
| 3 | """To run this example, you can start the vLLM server |
| 4 | without any specific flags: |
| 5 | |
| 6 | ```bash |
| 7 | vllm serve unsloth/Llama-3.2-1B-Instruct \ |
| 8 | --structured-outputs-config.backend outlines |
| 9 | ``` |
| 10 | |
| 11 | This example demonstrates how to generate chat completions |
| 12 | using the OpenAI Python client library. |
| 13 | """ |
| 14 | |
| 15 | from openai import OpenAI |
| 16 | |
| 17 | # Modify OpenAI's API key and API base to use vLLM's API server. |
| 18 | openai_api_key = "EMPTY" |
| 19 | openai_api_base = "http://localhost:8000/v1" |
| 20 | |
| 21 | tools = [ |
| 22 | { |
| 23 | "type": "function", |
| 24 | "function": { |
| 25 | "name": "get_current_weather", |
| 26 | "description": "Get the current weather in a given location", |
| 27 | "parameters": { |
| 28 | "type": "object", |
| 29 | "properties": { |
| 30 | "city": { |
| 31 | "type": "string", |
| 32 | "description": "The city to find the weather for" |
| 33 | ", e.g. 'San Francisco'", |
| 34 | }, |
| 35 | "state": { |
| 36 | "type": "string", |
| 37 | "description": ( |
| 38 | "the two-letter abbreviation for the state that the " |
| 39 | "city is in, e.g. 'CA' which would mean 'California'" |
| 40 | ), |
| 41 | }, |
| 42 | "unit": { |
| 43 | "type": "string", |
| 44 | "description": "The unit to fetch the temperature in", |
| 45 | "enum": ["celsius", "fahrenheit"], |
| 46 | }, |
| 47 | }, |
| 48 | "required": ["city", "state", "unit"], |
| 49 | }, |
| 50 | }, |
| 51 | }, |
| 52 | { |
| 53 | "type": "function", |
| 54 | "function": { |
| 55 | "name": "get_forecast", |
| 56 | "description": "Get the weather forecast for a given location", |
| 57 | "parameters": { |
| 58 | "type": "object", |
| 59 | "properties": { |
| 60 | "city": { |
| 61 | "type": "string", |
| 62 | "description": ( |
| 63 | "The city to get the forecast for, e.g. 'New York'" |
| 64 | ), |
| 65 | }, |
| 66 | "state": { |
| 67 | "type": "string", |
| 68 | "description": ( |
| 69 | "The two-letter abbreviation for the state, e.g. 'NY'" |
| 70 | ), |
| 71 | }, |
| 72 | "days": { |
| 73 | "type": "integer", |
| 74 | "description": "Number of days to get the forecast for (1-7)", |
| 75 | }, |
| 76 | "unit": { |
| 77 | "type": "string", |
| 78 | "description": "The unit to fetch the temperature in", |
| 79 | "enum": ["celsius", "fahrenheit"], |
| 80 | }, |
| 81 | }, |
| 82 | "required": ["city", "state", "days", "unit"], |
| 83 | }, |
| 84 | }, |
| 85 | }, |
| 86 | ] |
| 87 | |
| 88 | messages = [ |
| 89 | {"role": "user", "content": "Hi! How are you doing today?"}, |
| 90 | {"role": "assistant", "content": "I'm doing well! How can I help you?"}, |
| 91 | { |
| 92 | "role": "user", |
| 93 | "content": "Can you tell me what the current weather is in Dallas \ |
| 94 | and the forecast for the next 5 days, in fahrenheit?", |
| 95 | }, |
| 96 | ] |
| 97 | |
| 98 | |
| 99 | def main(): |
| 100 | client = OpenAI( |
| 101 | # defaults to os.environ.get("OPENAI_API_KEY") |
| 102 | api_key=openai_api_key, |
| 103 | base_url=openai_api_base, |
| 104 | ) |
| 105 | |
| 106 | models = client.models.list() |
| 107 | model = models.data[0].id |
| 108 | |
| 109 | chat_completion = client.chat.completions.create( |
| 110 | messages=messages, |
| 111 | model=model, |
| 112 | tools=tools, |
| 113 | tool_choice="required", |
| 114 | stream=True, # Enable streaming response |
| 115 | ) |
| 116 | |
| 117 | for chunk in chat_completion: |
| 118 | if chunk.choices and chunk.choices[0].delta.tool_calls: |
| 119 | print(chunk.choices[0].delta.tool_calls) |
| 120 | |
| 121 | chat_completion = client.chat.completions.create( |
| 122 | messages=messages, model=model, tools=tools, tool_choice="required" |
| 123 | ) |
| 124 | |
| 125 | print(chat_completion.choices[0].message.tool_calls) |
| 126 | |
| 127 | |
| 128 | if __name__ == "__main__": |
| 129 | main() |